Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 98 insertions, 48 deletions

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 76c0dade233f..95dd1f58c260 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -19,8 +19,6 @@
  *
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -202,6 +200,7 @@ static int tlb_initialize(struct bonding *bond)
 static void tlb_deinitialize(struct bonding *bond)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
+	struct tlb_up_slave *arr;
 
 	_lock_tx_hashtbl_bh(bond);
 
@@ -209,6 +208,10 @@ static void tlb_deinitialize(struct bonding *bond)
 	bond_info->tx_hashtbl = NULL;
 
 	_unlock_tx_hashtbl_bh(bond);
+
+	arr = rtnl_dereference(bond_info->slave_arr);
+	if (arr)
+		kfree_rcu(arr, rcu);
 }
 
 static long long compute_gap(struct slave *slave)
@@ -369,7 +372,7 @@ static int rlb_arp_recv(const struct sk_buff *skb, struct bonding *bond,
 	if (arp->op_code == htons(ARPOP_REPLY)) {
 		/* update rx hash table for this ARP */
 		rlb_update_entry_from_arp(bond, arp);
-		pr_debug("Server received an ARP Reply from client\n");
+		netdev_dbg(bond->dev, "Server received an ARP Reply from client\n");
 	}
 out:
 	return RX_HANDLER_ANOTHER;
@@ -448,11 +451,13 @@ static struct slave *__rlb_next_rx_slave(struct bonding *bond)
  */
 static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[])
 {
-	if (!bond->curr_active_slave)
+	struct slave *curr_active = bond_deref_active_protected(bond);
+
+	if (!curr_active)
 		return;
 
 	if (!bond->alb_info.primary_is_promisc) {
-		if (!dev_set_promiscuity(bond->curr_active_slave->dev, 1))
+		if (!dev_set_promiscuity(curr_active->dev, 1))
 			bond->alb_info.primary_is_promisc = 1;
 		else
 			bond->alb_info.primary_is_promisc = 0;
@@ -460,7 +465,7 @@ static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[])
 
 	bond->alb_info.rlb_promisc_timeout_counter = 0;
 
-	alb_send_learning_packets(bond->curr_active_slave, addr, true);
+	alb_send_learning_packets(curr_active, addr, true);
 }
 
 /* slave being removed should not be active at this point
@@ -509,7 +514,7 @@ static void rlb_clear_slave(struct bonding *bond, struct slave *slave)
 
 	write_lock_bh(&bond->curr_slave_lock);
 
-	if (slave != bond->curr_active_slave)
+	if (slave != bond_deref_active_protected(bond))
 		rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr);
 
 	write_unlock_bh(&bond->curr_slave_lock);
@@ -533,8 +538,8 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 				 client_info->slave->dev->dev_addr,
 				 client_info->mac_dst);
 		if (!skb) {
-			pr_err("%s: Error: failed to create an ARP packet\n",
-			       client_info->slave->bond->dev->name);
+			netdev_err(client_info->slave->bond->dev,
+				   "failed to create an ARP packet\n");
 			continue;
 		}
 
@@ -543,8 +548,8 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 		if (client_info->vlan_id) {
 			skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id);
 			if (!skb) {
-				pr_err("%s: Error: failed to insert VLAN tag\n",
-				       client_info->slave->bond->dev->name);
+				netdev_err(client_info->slave->bond->dev,
+					   "failed to insert VLAN tag\n");
 				continue;
 			}
 		}
@@ -628,8 +633,7 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
 		client_info = &(bond_info->rx_hashtbl[hash_index]);
 
 		if (!client_info->slave) {
-			pr_err("%s: Error: found a client with no channel in the client's hash table\n",
-			       bond->dev->name);
+			netdev_err(bond->dev, "found a client with no channel in the client's hash table\n");
 			continue;
 		}
 		/*update all clients using this src_ip, that are not assigned
@@ -684,7 +688,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
 			 * move the old client to primary (curr_active_slave) so
 			 * that the new client can be assigned to this entry.
 			 */
-			if (bond->curr_active_slave &&
+			if (curr_active_slave &&
 			    client_info->slave != curr_active_slave) {
 				client_info->slave = curr_active_slave;
 				rlb_update_client(client_info);
@@ -765,7 +769,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		tx_slave = rlb_choose_channel(skb, bond);
 		if (tx_slave)
 			ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr);
-		pr_debug("Server sent ARP Reply packet\n");
+		netdev_dbg(bond->dev, "Server sent ARP Reply packet\n");
 	} else if (arp->op_code == htons(ARPOP_REQUEST)) {
 		/* Create an entry in the rx_hashtbl for this client as a
 		 * place holder.
@@ -785,7 +789,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		 * updated with their assigned mac.
 		 */
 		rlb_req_update_subnet_clients(bond, arp->ip_src);
-		pr_debug("Server sent ARP Request packet\n");
+		netdev_dbg(bond->dev, "Server sent ARP Request packet\n");
 	}
 
 	return tx_slave;
@@ -1024,8 +1028,7 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	if (vid) {
 		skb = vlan_put_tag(skb, vlan_proto, vid);
 		if (!skb) {
-			pr_err("%s: Error: failed to insert VLAN tag\n",
-			       slave->bond->dev->name);
+			netdev_err(slave->bond->dev, "failed to insert VLAN tag\n");
 			return;
 		}
 	}
@@ -1039,7 +1042,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 	struct bonding *bond = bond_get_bond_by_slave(slave);
 	struct net_device *upper;
 	struct list_head *iter;
-	struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP];
+	struct bond_vlan_tag *tags;
 
 	/* send untagged */
 	alb_send_lp_vid(slave, mac_addr, 0, 0);
@@ -1067,10 +1070,12 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 		 * when strict_match is turned off.
 		 */
 		if (netif_is_macvlan(upper) && !strict_match) {
-			memset(tags, 0, sizeof(tags));
-			bond_verify_device_path(bond->dev, upper, tags);
+			tags = bond_verify_device_path(bond->dev, upper, 0);
+			if (IS_ERR_OR_NULL(tags))
+				BUG();
 			alb_send_lp_vid(slave, upper->dev_addr,
 					tags[0].vlan_proto, tags[0].vlan_id);
+			kfree(tags);
 		}
 	}
 	rcu_read_unlock();
@@ -1091,9 +1096,8 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
 	memcpy(s_addr.sa_data, addr, dev->addr_len);
 	s_addr.sa_family = dev->type;
 	if (dev_set_mac_address(dev, &s_addr)) {
-		pr_err("%s: Error: dev_set_mac_address of dev %s failed!\n"
-		       "ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
-		       slave->bond->dev->name, dev->name);
+		netdev_err(slave->bond->dev, "dev_set_mac_address of dev %s failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
+			   dev->name);
 		return -EOPNOTSUPP;
 	}
 	return 0;
@@ -1221,7 +1225,7 @@ static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *sla
  */
 static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slave *slave)
 {
-	struct slave *has_bond_addr = bond->curr_active_slave;
+	struct slave *has_bond_addr = rcu_access_pointer(bond->curr_active_slave);
 	struct slave *tmp_slave1, *free_mac_slave = NULL;
 	struct list_head *iter;
 
@@ -1267,13 +1271,12 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 	if (free_mac_slave) {
 		alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
 
-		pr_warn("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
-			bond->dev->name, slave->dev->name,
-			free_mac_slave->dev->name);
+		netdev_warn(bond->dev, "the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
+			    slave->dev->name, free_mac_slave->dev->name);
 
 	} else if (has_bond_addr) {
-		pr_err("%s: Error: the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n",
-		       bond->dev->name, slave->dev->name);
+		netdev_err(bond->dev, "the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n",
+			   slave->dev->name);
 		return -EFAULT;
 	}
 
@@ -1406,9 +1409,39 @@ out:
 	return NETDEV_TX_OK;
 }
 
+static int bond_tlb_update_slave_arr(struct bonding *bond,
+				     struct slave *skipslave)
+{
+	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
+	struct slave *tx_slave;
+	struct list_head *iter;
+	struct tlb_up_slave *new_arr, *old_arr;
+
+	new_arr = kzalloc(offsetof(struct tlb_up_slave, arr[bond->slave_cnt]),
+			  GFP_ATOMIC);
+	if (!new_arr)
+		return -ENOMEM;
+
+	bond_for_each_slave(bond, tx_slave, iter) {
+		if (!bond_slave_can_tx(tx_slave))
+			continue;
+		if (skipslave == tx_slave)
+			continue;
+		new_arr->arr[new_arr->count++] = tx_slave;
+	}
+
+	old_arr = rtnl_dereference(bond_info->slave_arr);
+	rcu_assign_pointer(bond_info->slave_arr, new_arr);
+	if (old_arr)
+		kfree_rcu(old_arr, rcu);
+
+	return 0;
+}
+
 int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
 	struct ethhdr *eth_data;
 	struct slave *tx_slave = NULL;
 	u32 hash_index;
@@ -1429,12 +1462,12 @@ int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 							      hash_index & 0xFF,
 							      skb->len);
 			} else {
-				struct list_head *iter;
-				int idx = hash_index % bond->slave_cnt;
+				struct tlb_up_slave *slaves;
 
-				bond_for_each_slave_rcu(bond, tx_slave, iter)
-					if (--idx < 0)
-						break;
+				slaves = rcu_dereference(bond_info->slave_arr);
+				if (slaves && slaves->count)
+					tx_slave = slaves->arr[hash_index %
+							       slaves->count];
 			}
 			break;
 		}
@@ -1575,7 +1608,7 @@ void bond_alb_monitor(struct work_struct *work)
 			 * use mac of the slave device.
 			 * In RLB mode, we always use strict matches.
 			 */
-			strict_match = (slave != bond->curr_active_slave ||
+			strict_match = (slave != rcu_access_pointer(bond->curr_active_slave) ||
 					bond_info->rlb_enabled);
 			alb_send_learning_packets(slave, slave->dev->dev_addr,
 						  strict_match);
@@ -1593,7 +1626,7 @@ void bond_alb_monitor(struct work_struct *work)
 
 		bond_for_each_slave_rcu(bond, slave, iter) {
 			tlb_clear_slave(bond, slave, 1);
-			if (slave == bond->curr_active_slave) {
+			if (slave == rcu_access_pointer(bond->curr_active_slave)) {
 				SLAVE_TLB_INFO(slave).load =
 					bond_info->unbalanced_load /
 						BOND_TLB_REBALANCE_INTERVAL;
@@ -1625,7 +1658,8 @@ void bond_alb_monitor(struct work_struct *work)
 			 * because a slave was disabled then
 			 * it can now leave promiscuous mode.
 			 */
-			dev_set_promiscuity(bond->curr_active_slave->dev, -1);
+			dev_set_promiscuity(rtnl_dereference(bond->curr_active_slave)->dev,
+					    -1);
 			bond_info->primary_is_promisc = 0;
 
 			rtnl_unlock();
@@ -1698,6 +1732,11 @@ void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave)
 		bond->alb_info.rx_slave = NULL;
 		rlb_clear_slave(bond, slave);
 	}
+
+	if (bond_is_nondyn_tlb(bond))
+		if (bond_tlb_update_slave_arr(bond, slave))
+			pr_err("Failed to build slave-array for TLB mode.\n");
+
 }
 
 /* Caller must hold bond lock for read */
@@ -1721,6 +1760,11 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char
 			 */
 		}
 	}
+
+	if (bond_is_nondyn_tlb(bond)) {
+		if (bond_tlb_update_slave_arr(bond, NULL))
+			pr_err("Failed to build slave-array for TLB mode.\n");
+	}
 }
 
 /**
@@ -1742,17 +1786,21 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	__acquires(&bond->curr_slave_lock)
 {
 	struct slave *swap_slave;
+	struct slave *curr_active;
 
-	if (bond->curr_active_slave == new_slave)
+	curr_active = rcu_dereference_protected(bond->curr_active_slave,
+						!new_slave ||
+						lockdep_is_held(&bond->curr_slave_lock));
+	if (curr_active == new_slave)
 		return;
 
-	if (bond->curr_active_slave && bond->alb_info.primary_is_promisc) {
-		dev_set_promiscuity(bond->curr_active_slave->dev, -1);
+	if (curr_active && bond->alb_info.primary_is_promisc) {
+		dev_set_promiscuity(curr_active->dev, -1);
 		bond->alb_info.primary_is_promisc = 0;
 		bond->alb_info.rlb_promisc_timeout_counter = 0;
 	}
 
-	swap_slave = bond->curr_active_slave;
+	swap_slave = curr_active;
 	rcu_assign_pointer(bond->curr_active_slave, new_slave);
 
 	if (!new_slave || !bond_has_slaves(bond))
@@ -1818,6 +1866,7 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct sockaddr *sa = addr;
+	struct slave *curr_active;
 	struct slave *swap_slave;
 	int res;
 
@@ -1834,23 +1883,24 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 	 * Otherwise we'll need to pass the new address to it and handle
 	 * duplications.
 	 */
-	if (!bond->curr_active_slave)
+	curr_active = rtnl_dereference(bond->curr_active_slave);
+	if (!curr_active)
 		return 0;
 
 	swap_slave = bond_slave_has_mac(bond, bond_dev->dev_addr);
 
 	if (swap_slave) {
-		alb_swap_mac_addr(swap_slave, bond->curr_active_slave);
-		alb_fasten_mac_swap(bond, swap_slave, bond->curr_active_slave);
+		alb_swap_mac_addr(swap_slave, curr_active);
+		alb_fasten_mac_swap(bond, swap_slave, curr_active);
 	} else {
-		alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr);
+		alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr);
 
 		read_lock(&bond->lock);
-		alb_send_learning_packets(bond->curr_active_slave,
+		alb_send_learning_packets(curr_active,
 					  bond_dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform clients mac address has changed */
-			rlb_req_update_slave_clients(bond, bond->curr_active_slave);
+			rlb_req_update_slave_clients(bond, curr_active);
 		}
 		read_unlock(&bond->lock);
 	}